AI Safety at the Frontier: Paper Highlights of October 2025
"知识编辑" 相关文章
Why Safety Constraints in LLMs Are Easily Breakable? Knowledge as a Network of Gated Circuits
Balancing Knowledge Updates: Toward Unified Modular Editing in LLMs
Believe It or Not: How Deeply do LLMs Believe Implanted Facts?
SAKE: Towards Editing Auditory Attribute Knowledge of Large Audio-Language Models
STEAM: A Semantic-Level Knowledge Editing Framework for Large Language Models
LLM Research Papers: The 2024 List
From Evaluation to Defense: Constructing Persistent Edit-Based Fingerprints for Large Language Models
A Dual-Axis Taxonomy of Knowledge Editing for LLMs: From Mechanisms to Functions
MultiMedEdit: A Scenario-Aware Benchmark for Evaluating Knowledge Editing in Medical VQA
Latent Knowledge Scalpel: Precise and Massive Knowledge Editing for Large Language Models
Knowledge Editing for Multi-Hop Question Answering Using Semantic Analysis
SAKE: Steering Activations for Knowledge Editing
NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database
DocTER: Evaluating Document-based Knowledge Editing
Retention analysis of edited knowledge after fine-tuning
Why Does New Knowledge Create Messy Ripple Effects in LLMs?
科学家提出模型编辑新算法，实现Llama 3在知识编辑任务表现提升35%
科学家提出模型编辑新算法，实现Llama 3在知识编辑任务表现提升35%
Updating and Editing Factual Knowledge in Language Models
